Reading (and watching) list for getting started on Generative AI and Prompting.
Introduction and Tools
- post Intro to Large Language Models : Andrej Karpathy’s introductory content on LLMs. Explain a lot of the terms you usually find when reading about LLMs: training, hallucination, tools, etc.
- post How I use LLMs : A two hour video from Andrej Karpathy sharing how different tools can be used. How search, deep research, and thinking work. How to choose your tools, and other information.
Building with GenAI
- post Building LLM applications for production : Chip Huyen has a lot of material on deploying Machine Learning models. This post is her considerations on moving LLM applications to production.
- post Common pitfalls when building generative AI applications : Chip Huyen ’s post on common mistakes.
- post Agents : Nice introduction about Agents, aligned with Anthropic’s ‘Building effective agents’.
- post Building effective agents : Anthropic’s lessons learned when building LLM agents.
Prompt Engineering
This section contains some information about Prompt Engineering, but keep in mind that as models improve, there is less need for complex techniques.
- site OpenAI Cookbook : Example code for executing tasks with the OpenAI API.
- course ChatGPT Prompt Engineering for Developers : DeepLearning.ai course on prompt engineering.
- post Brex’s Prompt Engineering Guide : Prompt engineering guide created by Brex. Contains a brief history of language models.
- post Prompt Engineering 101: Introduction and resources : Xavier Amatriain’s introduction to prompt engineering.
- book Prompt Engineering Guide : Online book with tips, applications, and examples of prompts.
- paper : A survey with different prompt engineering techniques.
Prompt Marketplaces
- site Roseta : My personal library with interesting prompts.
- site Snack Prompt : Prompt library with popularity system.
- site PromptBase : Prompt marketplace.
Libs and Frameworks
- site Ai Toolkit : AI Toolkit for TypeScript by Vercel.
- site Pydantic AI : Python agent framework that integrates well with Pydantic.
- site DSPy : DSPy is a Python framework for programming LLMs.
- site Guidance : Python lib with a language for interacting with different LLMs. It handles special tokens, output structure, and more.
Models and Systems
- post Open LLMs : List of LLMs licensed for commercial use.
- paper Sparks of Artificial General Intelligence: Early experiments with GPT-4 : Paper that discusses the emergent capabilities of GPT-4 and how this could be viewed as a primitive AGI.
- paper GPT-4 Technical Report : Technical report of GPT-4, its performance and limitations.
- paper LoRA: Low-Rank Adaptation of Large Language Models : Method that greatly reduce costs for fine-tuning large models.
- paper DeepSeek-V3 Technical Report : Insights on a Mixture-of-Experts model with 617B parameters and SOTA performance.
- paper DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models : DeepSeek paper that introduced Group Relative Policy Optimization (GRPO) for improving model performance.
- paper DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning : Reasoning models with SOTA performance.
Changelog
- [2025-03-09] Added ‘Building with GenAI’, and ‘Using GenAI Tools’ section. Updated libs and papers.
- [2023-05-19] Added more posts about systems and prompt engineering.
- [2023-05-08] Published first version.